Agent skill

ultra-research

多AI并行深度研究。当用户需要对某个主题进行全面调研、深度研究、多方对比、或需要覆盖多个维度和来源的综合分析时触发。适合复杂主题（技术选型、竞品分析、行业趋势、争议性话题等），不适合简单事实查询。通过多个AI服务并行研究，交叉验证，输出带引用的综合报告。

majiayu000534★ · 1 repos on radarProfile →
claude-coderead-onlyMIT
Install
npx skills add majiayu000/claude-skill-registry --skill ultra-research --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 6 KB
Bundled scripts: none
Allowed tools: -mcp__playwright__browser_navigate-mcp__playwright__browser_click-mcp__playwright__browser_type-mcp__playwright__browser_snapshot-mcp__playwright__browser_take_screenshot-mcp__playwright__browser_evaluate
Path: skills/analysis/ultra-research/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# 深度研究 Skill 三段式：**理解需求 → 迭代探索 → 整合报告**。 通过 Playwright MCP 控制多个 AI 服务进行并行研究。各服务交互细节见 reference 文件。 ## 前置条件 - **Playwright MCP** 需以持久化浏览器模式运行（`--user-data-dir`），这样各 AI 服务的登录态才会保留 - 用户需要**预先在 Playwright 浏览器中登录**要使用的 AI 服务（Gemini、ChatGPT、Claude、Grok）——不需要全部登录，登录了哪些就用哪些 - 本 skill 的选择器基于**中文 UI 环境**；英文 UI 下按钮名和 placeholder 会不同，需用 `browser_snapshot` 实时探测 ## 可用的 AI 服务与模式 | 服务 | 模式 | 耗时 | 特点 | |------|------|------|------| | Gemini Pro | 快速 | 10-60s | 快速问答、事实查证（有搜索能力） | | Gemini Deep Research | 深度 | 5-10min | 多源综合、广度覆盖 | | ChatGPT Thinking | 快速 | 10-120s | 深度推理、结构化分析 | | ChatGPT Deep Research | 深度 | 5-30min | 多源综合、广度覆盖 | | Claude Opus Extended | 快速 | 10-120s | 深度推理、方案设计 | | Grok 快速/专家 | 快速 | 10-60s | **X/Twitter 内容搜索**、时效性讨论和趋势 | | Grok DeepSearch | 深度 | 数分钟 | 深度搜索、社交媒体观点汇集 | **这些是工具箱，不是流水线。** 根据研究需要灵活选用和组合。 交互参考： - [references/gemini.md](references/gemini.md) — Gemini 操作、选择器、提取 - [references/chatgpt.md](references/chatgpt.md) — ChatGPT 操作（**最脆弱的服务，注意防御**） - [references/claude-web.md](references/claude-web.md) — Claude 操作、选择器、提取 - [references/grok.md](references/grok.md) — Grok 操作（**X/Twitter 内容搜索的独特入口**） - [references/extraction.md](references/extraction.md) — 通用提取技术（分块、引用链接、保存） - [refere

What's inside
Steps it walks through
  1. 前置条件
  2. 可用的 AI 服务与模式
  3. Part 1: 理解需求
  4. 先判断：用户的需求清楚吗？
  5. 构造查询
  6. 创建研究目录
  7. Part 2: 迭代探索
  8. 深度由进展决定
  9. 派发
  10. 轮询与提取
  11. 定向深入
  12. Tab 管理
  13. 何时停止
  14. Part 3: 整合报告
Ships with 1 file
  • metadata.json
More from claude-skill-registry
All skills →
descriptive-statisticsSummarizing and visualizing data through measures of center, spread, shape, and position. Covers…Data & Analyticsperplexity-researcher-reasoning-proHighest level of research and reasoning capabilities for complex decision-making with significant…OtherretroBrutally honest engineering retrospective. Analyzes git history for what actually happened — not…Data & AnalyticsanalyzeUniversal multi-perspective analyzer for any topic, file, idea, or decision. Extract key points…Otherarize-prompt-optimizationINVOKE THIS SKILL when optimizing, improving, or debugging LLM prompts using production trace data…Data & Analyticscellxgene-contextGuide for integrating CellxGene Census single-cell data with ENCODE bulk experiments. Use when…Data & Analytics
About this skill
What does the ultra-research skill do?

多AI并行深度研究。当用户需要对某个主题进行全面调研、深度研究、多方对比、或需要覆盖多个维度和来源的综合分析时触发。适合复杂主题（技术选型、竞品分析、行业趋势、争议性话题等），不适合简单事实查询。通过多个AI服务并行研究，交叉验证，输出带引用的综合报告。

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill ultra-research --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going
All skills →
The full catalog, by category and by tool.
Open Source Radar →
The repositories these skills come from, watched daily.
The people behind them →
Makers and builders across the ecosystem.